Gemma GGUF models
13341 GGUF models in the Gemma family, quantized by 4460 uploaders. Sizes run from 2M to 70.6B parameters. The longest trained context is 1280000K tokens.
About the Gemma GGUF models
Gemma is represented on ggufmodels.com by 13,341 GGUF models, quantized by 4,460 uploaders on Hugging Face. The most downloaded are Gemma-4-12B-It, Gemma-4-26B-A4B-It and gemma 4 E4B it qat q4 0. Parameter counts run from 2M to 70.6B, and the longest trained context window is 1280000K tokens.
A Q4_K_M file of a Gemma model is between 0.0 to 42.5 GB, which is the quant most people start with. Most files come from mradermacher (3169), RichardErkhov (671) and featherless-ai-quants (277). The quants you will meet most often are Q4_K_M (8877), Q8_0 (6571), Q5_K_M (6019) and Q6_K (5964), where the number is how many models offer that quant.
Frequently asked questions
Which Gemma GGUF should I download?
The most downloaded Gemma GGUF here is Gemma-4-12B-It. Pick the size that fits your GPU first, then choose a quant: Q4_K_M is the usual starting point, and Q5_K_M or Q6_K give more quality if you have memory to spare. The VRAM pages below list what fits each GPU.
How much VRAM does a Gemma model need?
Q4_K_M files of Gemma models on this site range from 0.0 to 42.5 GB. Add the KV cache for your context length and about 0.5 GB for the runtime, which usually means 1.5 to 3 GB on top of the file at an 8K context.
Where do Gemma GGUF files come from?
The most common quantizers here are mradermacher, RichardErkhov and featherless-ai-quants. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.